计算机科学
蒸馏
可扩展性
多样性(控制论)
深度学习
人工智能
人工神经网络
比例(比率)
机器学习
编码
数据科学
数据库
基因
物理
有机化学
化学
量子力学
生物化学
作者
Jianping Gou,Baosheng Yu,Stephen J. Maybank,Dacheng Tao
标识
DOI:10.1007/s11263-021-01453-z
摘要
In recent years, deep neural networks have been successful in both industry and academia, especially for computer vision tasks. The great success of deep learning is mainly due to its scalability to encode large-scale data and to maneuver billions of model parameters. However, it is a challenge to deploy these cumbersome deep models on devices with limited resources, e.g., mobile phones and embedded devices, not only because of the high computational complexity but also the large storage requirements. To this end, a variety of model compression and acceleration techniques have been developed. As a representative type of model compression and acceleration, knowledge distillation effectively learns a small student model from a large teacher model. It has received rapid increasing attention from the community. This paper provides a comprehensive survey of knowledge distillation from the perspectives of knowledge categories, training schemes, teacher–student architecture, distillation algorithms, performance comparison and applications. Furthermore, challenges in knowledge distillation are briefly reviewed and comments on future research are discussed and forwarded.
科研通智能强力驱动
Strongly Powered by AbleSci AI